cesarsal1nas/Qwen3.8-27B-EXL3-GGUF
Not comparable yet vs GestaltLabs/Qwen3.8-27B-EXL3-11.5GB. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (514 of 3080/1684 match), usually an architecture llama.cpp's name map doesn't cover yet.